Geometry-aware Two-scale PIFu Representation for Human Reconstruction

Authors: Zheng Dong, Ke Xu, Ziheng Duan, Hujun Bao, Weiwei Xu, Rynson Lau

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate the effectiveness of our approach in reconstructing facial details and bodies of different poses and its superiority over state-of-the-art methods.
Researcher Affiliation Academia Zheng Dong1 Ke Xu2 Ziheng Duan1 Hujun Bao1 Weiwei Xu 1 Rynson W.H. Lau2 1State Key Lab of CAD&CG, Zhejiang University 2 City University of Hong Kong
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [No]
Open Datasets Yes We use the THuman2.0 [100] dataset which contains 500 high-quality 3D human scans to train and validate our network. We split the dataset into training and test sets with a ratio of 4:1. For PIFu-Face, we pretrain Ff using the Face Scape [94] dataset, which contains 3D head models of different people and expressions.
Dataset Splits No We use the THuman2.0 [100] dataset which contains 500 high-quality 3D human scans to train and validate our network. We split the dataset into training and test sets with a ratio of 4:1.
Hardware Specification No This information is provided in the supplemental material.
Software Dependencies No The paper does not list specific software dependencies with version numbers in the main text.
Experiment Setup No We explain the implementation details in the supplemental material.